© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 15466
    Prev
    Next
    INDEX
    Explanations

    references to legal fees and costs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Expense
    -0.69
     suon
    -0.68
    ViewFeatures
    -0.65
     îns
    -0.62
    Jar
    -0.61
     Kew
    -0.60
     Jar
    -0.57
     Gables
    -0.57
     Ghat
    -0.56
    Spreadsheet
    -0.56
    POSITIVE LOGITS
     costs
    1.33
     Costs
    1.19
    costs
    1.17
     COSTS
    1.13
    Costs
    1.09
     interests
    0.91
    '][$
    0.83
    interests
    0.80
    BagConstraints
    0.80
    </tfoot>
    0.78
    Activations Density 0.068%

    No Known Activations